Senior AI/ML Engineer - GenAI/Agentic AI
First seen by Alion on Oct 5, 2026.
Role : Senior AI/ML Engineer - GenAI / LLM / Agentic AI
Location : Whitefield, Bangalore
Work Mode : Hybrid - 3 days/week from office
Experience : 6+ years overall, including 3+ years in production-grade LLM/GenAI engineering
About the Role :
We are looking for a Senior AI/ML Engineer to join our AI Platform team and build production-grade AI agents for financial close automation.
This is a hands-on engineering role for someone who has moved beyond LLM demos and experimentation and has experience designing, building, deploying, and monitoring reliable LLM/agentic AI systems in production.
You will work with a cross-functional engineering squad and own the LLM and agent layer, including agent orchestration, RAG, LLM integrations, evaluation, observability, guardrails, and production deployment.
What You'll Work On :
- Design and build multi-step AI agent workflows using LangChain and LangGraph
- Implement agent tools, state management, routing, handoffs, and human-in-the-loop workflows
- Integrate Azure OpenAI and other frontier LLMs such as Claude, Gemini, or Mistral
- Work with structured outputs, function/tool calling, prompt engineering, token optimization, and latency optimization
- Build production-grade RAG pipelines covering document ingestion, embeddings, retrieval, and generation
- Work with vector databases such as pgvector, Pinecone, Qdrant, Weaviate, or FAISS
- Implement LLM observability and tracing using Langfuse or equivalent platforms
- Build evaluation frameworks and regression testing for prompts, models, and RAG pipelines
- Implement guardrails, confidence thresholds, fallbacks, and human escalation mechanisms
- Ensure agent decisions and tool calls are traceable and auditable
- Build AI/agent service APIs using Python and FastAPI
- Work with PostgreSQL and agent state/audit data
- Containerize and deploy services using Docker and Kubernetes
- Work with Azure DevOps CI/CD for automated build and deployment
- Collaborate with architects and software engineers on agent orchestration and communication patterns
Must-Have Skills :
- 6+ years of overall software engineering experience
- 3+ years of hands-on experience building and deploying production LLM/GenAI applications
- Strong hands-on experience with LangChain and LangGraph
- Experience building production-grade AI agents/agentic workflows
- Strong Python development experience
- Experience with Azure OpenAI or other LLM APIs
- Hands-on experience with RAG
- Experience with at least one vector database : pgvector / Pinecone / Qdrant / Weaviate / FAISS
- Experience with LLM observability/evaluation tools such as Langfuse
- Understanding of prompt versioning, evaluation, regression testing, and model/prompt lifecycle management
- Experience with guardrails, fallback handling, confidence thresholds, and traceability
- Experience with FastAPI or equivalent Python async frameworks
- Experience with PostgreSQL
- Experience with Docker and Kubernetes
- Experience with CI/CD, preferably Azure DevOps
Good to Have :
- Hands-on exposure to MCP (Model Context Protocol) and/or A2A (Agent-to-Agent)
- Experience with Google ADK, AutoGen, CrewAI, or Semantic Kernel
- Experience in financial/accounting applications
- Understanding of SOX/GDPR requirements for AI auditability
- Experience with LLM fine-tuning or federated learning
- Open-source contributions to AI/LLM/agent frameworks
Important :
This position is not focused on traditional ML research or LLM experimentation/POCs.
We are specifically looking for engineers who have built and shipped reliable, observable, and production-ready LLM/agent systems.
Skills
Generative AI, LLM, Agentic AI, Python, LangChain, FastAPI, RAG, PostgreSQL, LangGraph, Artificial Intelligence, Machine Learning