AI Engineer

Bounteous; Bengaluru; On-site; INR 3,500,000 - 6,500,000; Full time

Benefits offered by this job

OpenAI model access

AWS infrastructure experience

Job summary

Bounteous is seeking a seasoned software engineer to design and launch GenAI agentic solutions for large-scale production environments. You will build tool-calling agents, integrate with observability, and collaborate with production teams to translate pain points into actionable AI roadmaps.

You will ensure safety, reliability, and governance, optimize costs and latency, and mentor others in agent architectures and evaluation practices.

Qualifications

• 5+ years of software development in one or more languages (Python, C/C++, Go, Java).
• 3+ years designing, architecting, and launching production ML systems, including model deployment/serving and monitoring.
• Practical experience with Large Language Models (LLMs) — API integration, prompt engineering, fine-tuning/adaptation, and building applications using RAG and tool-using agents.
• Understanding of different LLMs (OpenAI, Gemini, Llama, Qwen, Claude).
• Solid grasp of applied statistics, core ML concepts, algorithms, and data structures.
• Strong analytical problem-solving, ownership, and ability to communicate complex ideas across global teams.
• Preferred: AWS, containerized services (ECS/EKS), serverless (Lambda), data services (S3, DynamoDB, Redshift), orchestration (Step Functions), model serving (SageMaker), and infra-as-code (Terraform/CloudFormation).
• 5+ years of software development experience, including 3+ years designing and launching production ML systems.

Responsibilities

• Design and implement tool-calling agents that combine retrieval, structured reasoning, and secure action execution (function calling, change orchestration, policy enforcement) following the MCP protocol.
• Engineer robust guardrails for safety, compliance, and least-privilege access.
• Build an evaluation framework for open-source and foundational LLMs.
• Implement retrieval pipelines, prompt synthesis, response validation, and self-correction loops tailored to production operations.
• Connect agents to observability, incident management, and deployment systems.
• Enable automated diagnostics, runbook execution, remediation, and post-incident summarization with full traceability.
• Partner with production engineers and application teams to translate production pain points into agentic AI roadmaps.
• Define objective functions linked to reliability, risk reduction, and cost.
• Deliver auditable, business-aligned outcomes.
• Build validator models, adversarial prompts, and policy checks into the stack.
• Enforce deterministic fallbacks, circuit breakers, and rollback strategies.
• Instrument continuous evaluations for usefulness, correctness, and risk.
• Optimize cost and latency via prompt engineering, context management, caching, model routing, and distillation.
• Leverage batching, streaming, and parallel tool-calls to meet stringent SLOs under real-world load.
• Curate domain knowledge and build a data-quality validation framework.
• Establish feedback loops and a milestone framework to maintain knowledge freshness.
• Drive design reviews, experiment rigor, and high-quality engineering practices.
• Mentor peers on agent architectures, evaluation methodologies, and safe deployment patterns.

Skills

Python

C/C++

Go

Java

LLMs

OpenAI

Gemini

Llama

Qwen

Claude

Tool-using agents

Tools

OpenAI

Gemini

Llama

Qwen

Claude

AWS

ECS/EKS

SageMaker

Terraform

CloudFormation

S3

DynamoDB

Redshift

Step Functions

Job description

5 to 9 years of experience
Skills: Python, C/C++, Go, Java, OpenAI, Gemini, Llama, Qwen, Claude

Role Overview

In this role, you will be responsible for launching and implementing GenAI agentic solutions aimed at reducing the risk and cost of managing large-scale production environments with varying complexities. You will address production runtime challenges by developing agentic AI solutions that can diagnose, reason, and take action in production environments — improving productivity and resolving production support issues.

What You'll Do

Build Agentic AI Systems

• Design and implement tool-calling agents that combine retrieval, structured reasoning, and secure action execution (function calling, change orchestration, policy enforcement) following the MCP protocol
• Engineer robust guardrails for safety, compliance, and least-privilege access
• Build an evaluation framework for open-source and foundational LLMs
• Implement retrieval pipelines, prompt synthesis, response validation, and self-correction loops tailored to production operations

Integrate with Runtime Ecosystems

• Connect agents to observability, incident management, and deployment systems
• Enable automated diagnostics, runbook execution, remediation, and post-incident summarization with full traceability

Collaborate Directly with Users

• Partner with production engineers and application teams to translate production pain points into agentic AI roadmaps
• Define objective functions linked to reliability, risk reduction, and cost
• Deliver auditable, business-aligned outcomes

Safety, Reliability, and Governance

• Build validator models, adversarial prompts, and policy checks into the stack
• Enforce deterministic fallbacks, circuit breakers, and rollback strategies
• Instrument continuous evaluations for usefulness, correctness, and risk

Scale and Performance

• Optimize cost and latency via prompt engineering, context management, caching, model routing, and distillation
• Leverage batching, streaming, and parallel tool-calls to meet stringent SLOs under real-world load

Build a RAG Pipeline

• Curate domain knowledge and build a data-quality validation framework
• Establish feedback loops and a milestone framework to maintain knowledge freshness

Raise the Bar

• Drive design reviews, experiment rigor, and high-quality engineering practices
• Mentor peers on agent architectures, evaluation methodologies, and safe deployment patterns

Role Requirements

• Software Development: 5+ years of software development in one or more languages (Python, C/C++, Go, Java); strong hands-on experience building and maintaining large-scale Python applications preferred
• ML Systems: 3+ years designing, architecting, testing, and launching production ML systems, including model deployment/serving, evaluation and monitoring, data processing pipelines, and model fine-tuning workflows
• LLM Experience: Practical experience with Large Language Models (LLMs) — API integration, prompt engineering, fine-tuning/adaptation, and building applications using RAG and tool-using agents (vector retrieval, function calling, secure tool execution)
• Model Knowledge: Understanding of different LLMs, both commercial and open source, and their capabilities (e.g., OpenAI, Gemini, Llama, Qwen, Claude)
• Foundational Knowledge: Solid grasp of applied statistics, core ML concepts, algorithms, and data structures to deliver efficient and reliable solutions
• Core Competencies: Strong analytical problem-solving, ownership, and urgency; ability to communicate complex ideas simply and collaborate effectively across global teams with a focus on measurable business impact
• Preferred: Proficiency building and operating on cloud infrastructure (ideally AWS), including containerized services (ECS/EKS), serverless (Lambda), data services (S3, DynamoDB, Redshift), orchestration (Step Functions), model serving (SageMaker), and infra-as-code (Terraform/CloudFormation)
• 5+ years of software development experience, including 3+ years designing and launching production ML systems

Why do I get up every morning excited to start my day at Bounteous? I am able to have an impact - to my teams, clients, and Bounteous. To me, that means I am able to contribute to something bigger than myself. I can ask questions, challenge the status quo, and contribute to new ways of doing things. Working with teams of energetic, fun, and innovative people collaborating to solve some of the most challenging problems that our clients and Bounteous face is truly rewarding! My roles here have allowed me the opportunity to challenge myself, grow, and contribute to a better Bounteous.