Applied AI Engineer

InterviewSarthi

Brasil

Remote

BRL 180,000 - 320,000

Full time

2 days ago
Be an early applicant

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Benefits offered by this job

Fully remote working arrangement

Job summary

Interviewsarthi in Brazil is seeking an Applied AI Engineer to translate complex learning scenarios into robust AI workflows. You will own conversational behavior, integration architecture, testing, and production readiness while collaborating with cross-functional teams to ensure AI-powered experiences are reliable.

The role emphasizes prompt engineering, RAG, and grounded outputs, with an emphasis on safety, privacy, and measurable results.

Qualifications

  • Hands-on with LLM-powered applications and multi-step workflows.
  • Experience with prompt engineering and evaluation.
  • Knowledge of RAG architecture, grounding, and citation.

Responsibilities

  • Translate scenarios, prompts, and schemas into robust AI workflows.
  • Define how AI models interact with services and data sources.
  • Design system prompts, outputs, and validation to prevent invalid results.
  • Move validated prototypes into production with Engineering collaboration.
  • Monitor AI performance and ensure safety, privacy, and compliance.

Skills

Python
Machine learning
LLMs
Prompt engineering
JSON Schema
APIs

Tools

Git
Bitbucket
Python
TypeScript
API integrations

Job description

Got this interview? Our apps help you get the job.

Read from the description itself, not inferred.

This role on the market

1,450 open applied roles across 189 companies are on ApplySarthi right now, most of them in Bengaluru (90), Hyderabad (15), Delhi NCR (8).

What applied roles keep asking for: Python (63%), Machine learning (47%), LLMs (39%), Java (31%), C++ (29%), Deep learning (23%), AWS (22%), Generative AI (18%) — counted across their open postings here.

Counted across 14 company job boards, updated as roles open and close.

Preparing for this interview

Interviews for applied roles keep coming back to Python, Machine learning, LLMs, Java. Practise those questions before you sit with Jobgether.

Questions you are likely to be asked
  • Why do you want to join Jobgether?
  • What is your experience with LLMs? Tell me one thing you learned the hard way.
  • Walk me through a model you built, from the data to how it was used.
  • How did you know your model was actually good, and not just good on your test set?
  • Tell me about a time the data was messy or wrong. What did you do?

Prep Sarthi gives you a free mock interview: an AI interviewer asks youquestions like these out loud, from your own CV and this job, and shows your score and your weakest answer.

Accountabilities:: As an Applied AI Engineer, you will translate complex learning scenarios and product requirements into robust AI workflows. You will take ownership of conversational behavior, integration architecture, testing, and production readiness while collaborating with cross-functional teams to ensure that AI-powered experiences remain reliable and aligned with their intended purpose. Translate scenario specifications, decision models, and assessment rubrics into prompts, application logic, and testable AI behaviors. Identify missing requirements, technical constraints, and potential risks, escalating them to Product, Engineering, and subject-matter experts. Define how AI models interact with application services and approved data sources, including APIs, tools, data structures, validation rules, error handling, and permitted actions. Design system prompts, structured outputs, and validation mechanisms to detect and prevent invalid responses from reaching learners. Build conversational runtimes with controlled personas, session state, and clearly defined state transitions. Separate simulation behavior, assessment logic, and feedback mechanisms to ensure that feedback does not influence assessment outcomes. Implement retrieval-augmented generation (RAG) and grounding from approved knowledge sources, including source references where required. Maintain version control and documentation for code, prompts, schemas, and evaluation assets. Run structured experiments with Product teams, defining clear objectives and measurable success criteria. Move validated prototypes into production in collaboration with Engineering and verify that deployed behavior remains consistent. Contribute to technical controls supporting accreditation and compliance requirements, including issue flagging, review workflows, disclosures, and logging. Monitor and evaluate AI performance, identifying opportunities to improve quality, reliability, security, and efficiency. Requirements : The ideal candidate has hands-on experience developing LLM-powered applications and multi-step conversational workflows. You combine strong technical expertise in prompt engineering, agentic systems, retrieval, and evaluation with sound judgment around AI safety, privacy, and human oversight. You are comfortable collaborating with both technical and non-technical stakeholders and can communicate complex trade-offs clearly. Expert-level prompt and context engineering, including system prompts, few-shot examples, prompt chaining, routing, and breaking complex tasks into manageable steps. Strong experience with structured outputs, JSON Schema, function calling, validation layers, and retry and fallback mechanisms. Practical knowledge of RAG architecture, including chunking, metadata filtering, hybrid search, reranking, and citation grounding. Experience managing token budgets, prompt caching, context compaction, and long-session memory. Expertise in agentic systems, including tool use, planner/executor patterns, multi-agent orchestration, state machines, and human-in-the-loop checkpoints. Ability to define tool schemas, permission scopes, and action limits for AI agents. Experience with AI evaluation methods such as golden datasets, rubric-based scoring, LLM-as-judge calibrated against human reviewers, and regression testing. Familiarity with LLM observability, tracing, and performance monitoring. Strong understanding of LLM security risks, including prompt injection, data leakage, jailbreaks, unsafe tool actions, and guardrails. Ability to compare prompting, retrieval, and model options based on quality, latency, and cost. Proficiency in Python or TypeScript, including API integrations and automated testing. Experience with Git-based version control (such as Bitbucket), reproducible tests, and continuous integration. Comfortable using AI coding agents as part of your standard development workflow. Strong communication skills, with the ability to explain technical decisions and trade-offs to non-technical colleagues. Sound judgment regarding privacy, human oversight, and the limitations of AI-generated assessments or advice. Demonstrated experience building LLM applications with multi-step conversational workflows. Experience collaborating with subject-matter experts to translate domain knowledge into effective AI behavior. Preferred Qualifications: Background in learning technology products, professional assessment, conversational simulations, or regulated industry content. Benefits : Fully remote working arrangement. Long-term professional opportunity. Opportunity to build and improve AI-powered learning experiences used in regulated professional industries. Collaborative, Agile-oriented environment with cross-functional teams. Exposure to advanced LLM applications, conversational agents, and applied AI development challenges.

Match this job to your CV

ApplySarthi scores your CV against this role, shows the skills you are missing, and writes a tailoredversion for the application.

Need answers during your interview? Try Live Sarthi.

Live Sarthi, an Interview Sarthi app, shows answer suggestions during the call.

  • Hidden from supported screen sharing The overlay stays out of supported Windows screen captures.
  • Answers start in about 1.5 seconds Response time varies with your connection and model.
  • From your own CV Your projects and your experience, not a generic script.
  • 30 minutes free Then ₹149 for a 2-day pass with unlimited calls — you pay for the days you are interviewing, not a subscription.

A Windows app, from the same team as ApplySarthi.

Listed on lever· posted 2026-11-15.ApplySarthi collects openings and links to application pages; the role is advertised byJobgether, not by us.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Technical Product Manager, Identification & JS Agent
Technical Product Manager, Identification & JS Agent

InterviewSarthi • Brazil

Remote
BRL 720,000 - 971,000
Fully remote working environment
Opportunity to work on advanced ID/JS技
B2B Lead Generation & Sales Prospecting Virtual Assistant
B2B Lead Generation & Sales Prospecting Virtual Assistant

InterviewSarthi • Brazil

Remote
BRL 83,000 - 165,000
Weekly payments
Remote independent contractor
Part-time schedule 10–20 hours/week
GTM Marketing Manager, Google Cloud
GTM Marketing Manager, Google Cloud

InterviewSarthi • Brazil

Remote
BRL 514,000 - 629,000
Fully remote
Annual bonus 10%
Career development
+1
Demand Planner
Demand Planner

InterviewSarthi • Brazil

Remote
BRL 457,000 - 514,000
Fully remote
Bonus
Applied AI Engineer
Applied AI Engineer

Jobgether • Brazil

Remote
BRL 180,000 - 300,000
Fully remote work arrangement
Long-term professional opportunity
Exposure to advanced LLM applications
Applied AI Engineer
Applied AI Engineer

AItoolnavio • Brazil

Remote
BRL 180,000 - 300,000
Fully remote
Long-term opportunity
Agile environment
Staff Data Scientist, Agent Improvement Loop
Staff Data Scientist, Agent Improvement Loop

Jobgether • Brazil

Remote
BRL 320,000 - 520,000
Unlimited PTO
Fully remote
Flexible hours around Central Time
+1
AI Consultant (Lead) ID35730
AI Consultant (Lead) ID35730

AgileEngine, LLC. • Porto Alegre

Hybrid
BRL 780,000 - 1,196,000
Professional growth opportunities
Competitive USD-based compensation
Flexible working schedule
AI Consultant (Lead) ID35730
AI Consultant (Lead) ID35730

AgileEngine, LLC. • Campinas

Hybrid
BRL 180,000 - 240,000
Professional growth opportunities
Competitive compensation
Flexible working hours
Staff Software Engineer, Product
Staff Software Engineer, Product

Jobgether • Brazil

Remote
BRL 474,000 - 697,000
Fully Remote Work