Junior Applied AI Engineer (LLM Systems)

Encora; United States; Remote; USD 60.000 - 90.000; Vollzeit

Zusammenfassung

Coforge is hiring a Junior Applied AI Engineer (LLM Systems) for remote work in LATAM. You will design evaluation frameworks for AI agents, build guardrails, and develop prompts while collaborating with Engineering, Data Science, and Compliance teams to ensure reliable, compliant AI solutions.

The role emphasizes hands-on work with LLMs, AWS Bedrock, Langfuse, and MCP integrations, with a strong focus on safety and production readiness.

Qualifikationen

• 1-3+ years in AI/ML, Applied AI, Data Science.
• Experience with LLMs and AI-powered apps.
• Knowledge of LLM evaluation techniques, benchmarks, scoring.
• Understanding multi-turn AI agent behavior & tool-calling.
• Prompt engineering, structured outputs, and prompt optimization.
• AI safety concepts including moderation, prompt injection prevention, jailbreak mitigation, and guardrails.
• Hands-on experience with AWS cloud services, preferably Bedrock.
• Experience with Langfuse or similar observability platforms for LLM apps.
• Strong programming skills in Python.
• Knowledge of software engineering best practices including unit testing, code reviews, and Git workflows.
• Advanced English communication skills.

Aufgaben

• Design and execute evaluation frameworks for AI agents, including test datasets and regression testing.
• Build, configure, and optimize AI guardrails and moderation systems for regulated domains.
• Develop, test, and improve prompts based on evaluation results and production trace analysis.
• Create MCP servers and tool integrations enabling AI agents to access internal data and services.
• Support fine-tuning and evaluation of language models using domain-specific data.
• Prototype and validate AI workflows using System One models Jev and Laya for classification, routing, and verification.
• Monitor AI system quality, latency, performance, and costs via Langfuse and improve where needed.
• Collaborate with Engineering, Data Science, and Compliance to ensure reliable and compliant AI solutions.

Kenntnisse

LLMs

Generative AI

Prompt Engineering

AI Agent Evaluation

Python

FastAPI

Guardrails & Moderation

REST APIs

Git

MCP

Langfuse

AWS Bedrock

Tools

AWS Bedrock

Langfuse

MCP

Jev

Laya

Jobbeschreibung

Latin America

Job Title

Key Skills

LLMs, Generative AI, AWS Bedrock, Prompt Engineering, AI Agent Evaluation, Langfuse, Python, FastAPI, MCP, Guardrails & Moderation, REST APIs, Git

Experience

1-3+ years of experience in AI/ML Engineering, Applied AI, Data Science, or related fields.

Location

LATAM (Remote)

Mode

Remote

We at Coforge are hiring Junior Applied AI Engineer (LLM Systems) (20848-10-1) with the following skill set.

Key Responsibilities

• Design and execute evaluation frameworks for AI agents, including test datasets, LLM-as-a-Judge methodologies, human reviews, and regression testing.
• Build, configure, and optimize AI guardrails and moderation systems for regulated domains such as financial services and credit products.
• Develop, test, and continuously improve prompts based on evaluation results and production trace analysis.
• Create and maintain MCP (Model Context Protocol) servers and tool integrations that enable AI agents to interact with internal data and services.
• Support fine-tuning and evaluation of language models using domain-specific datasets.
• Prototype and validate AI workflows using System One models such as Jev and Laya for classification, routing, and verification tasks.
• Monitor AI system quality, latency, performance, and costs through Langfuse and implement improvement initiatives.
• Collaborate with Engineering, Data Science, and Compliance teams to ensure AI solutions are reliable, secure, and compliant.

Required Skills & Qualifications

• 1-3+ years of experience in Machine Learning, Applied AI, Data Science, or Software Engineering.
• Experience working with Large Language Models (LLMs) and AI-powered applications.
• Knowledge of LLM evaluation techniques, including benchmark datasets, scoring frameworks, and LLM-as-a-Judge approaches.
• Understanding of AI agent behavior across multi-turn conversations and tool-calling workflows.
• Experience with prompt engineering, structured outputs, and prompt optimization.
• Familiarity with AI safety concepts including moderation, prompt injection prevention, jailbreak mitigation, and guardrails.
• Hands-on experience with AWS cloud services, preferably Amazon Bedrock.
• Experience with Langfuse or similar observability and evaluation platforms for LLM applications.
• Strong programming skills in Python.
• Knowledge of software engineering best practices including unit testing, code reviews, and Git-based development workflows.
• Advanced English communication skills (written and verbal).

Preferred Skills

• Hands-on experience with fine-tuning LLMs using techniques such as LoRA or full fine-tuning.
• Familiarity with Small Language Models (SLMs), model distillation, and deployment strategies.
• Exposure to System One models such as Jev and Laya.
• Experience in financial services, fintech, banking, or other regulated industries.
• Knowledge of AI evaluation, observability, and production monitoring best practices.

At Coforge, we hire professionals based solely on their skills and qualifications and do not discriminate based on age, disability, religion, gender, sexual orientation, socioeconomic status, or nationality.