The Role
As an AI/ML Engineer, you will help build and implement the AI capabilities that power our agentic AI platform. You will work closely with AI/ML architects, founding team, data engineers, and platform engineers to develop agent workflows, retrieval pipelines, evaluation routines, and production-ready AI components.
This is a hands-on engineering role for someone who is comfortable building with modern AI/ML and LLM frameworks, agentic AI systems, experimenting with models and prompts, and translating design patterns into working software. The role is ideal for an engineer who wants to work on real-world enterprise AI systems rather than isolated demos.
Key Responsibilities
- Build and enhance AI agent workflows using frameworks such as LangGraph, LangChain, AutoGen, CrewAI, or equivalent technologies.
- Implement AI agents for data discovery, profiling, enrichment, extraction, classification, contextual reasoning, and enterprise knowledge discovery.
- Develop retrieval-augmented generation pipelines, including document chunking, embedding generation, metadata tagging, vector indexing, retrieval tuning, and response generation.
- Work with vector databases such as Pinecone, Milvus, Qdrant, Weaviate, pgvector, Chroma, or equivalent technologies.
- Build structured data agents that can connect to databases, inspect schemas, generate SQL, and support semantic understanding of enterprise data.
- Implement document intelligence workflows for PDFs, Word documents, emails, transcripts, logs, and semi-structured enterprise content using Azure Document Intelligence, AWS Textract, LlamaParse, or equivalent tools.
- Support prompt engineering, prompt testing, prompt versioning, and reusable prompt template development.
- Implement AI evaluation routines covering answer quality, retrieval quality, hallucination checks, regression tests, robustness checks, and response consistency.
- Support integration with LLM APIs and open-source models from providers such as OpenAI, Anthropic, Azure OpenAI, Hugging Face, Llama, Gemma, or equivalent ecosystems.
- Help implement AI safety and trust controls, including guardrails, prompt injection checks, data leakage prevention patterns, and policy-based response controls.
- Collaborate with data engineers to prepare AI agents to clean, contextualize, and structure enterprise data.
- Collaborate with DevOps and platform engineers to containerize, deploy, monitor, and troubleshoot AI services.
- Write clean, modular, testable Python code and participate in code reviews, sprint ceremonies, and engineering design discussions.
- Stay current with emerging tools and patterns in LLMs, agentic AI, RAG, evaluation frameworks, and enterprise AI deployment.
Must-Have Qualifications
- Min 7 years of experience in software engineering, AI/ML engineering, applied machine learning, data science engineering, or related technology roles.
- Strong hands-on programming experience in Python and building AI agents.
- Practical exposure to LLMs, RAG, vector databases, embedding models, prompt engineering, and AI application development.
- Experience with one or more AI/LLM frameworks such as LangChain, LangGraph, LlamaIndex, AutoGen, CrewAI, Semantic Kernel, or equivalent tools.
- Working knowledge of REST APIs, microservices, Git-based development, unit testing, and modern software engineering practices.
- Familiarity with SQL and structured data concepts, including tables, schemas, joins, relationships, and query generation.
- Exposure to document processing, text extraction, semantic search, information retrieval, or NLP-based workflows.
- Understanding of basic AI evaluation concepts such as precision, recall, retrieval quality, hallucination checks, and test datasets.
- Ability to work in an agile, fast-moving product engineering environment with high ownership and ambiguity.
- Strong problem-solving skills and willingness to learn new AI, data, and platform technologies quickly.
Good to Have
- Experience with Azure OpenAI, AWS Bedrock, Google Vertex AI, or equivalent enterprise AI platforms.
- Exposure to open-source LLMs, Hugging Face, vLLM, Ollama, or model-serving frameworks.
- Experience with RAG evaluation tools such as RAGAS, DeepEval, Promptfoo, LangSmith, or equivalent frameworks.
- Exposure to knowledge graphs, ontologies, metadata models, or semantic data layers.
- Experience with Docker, Kubernetes, CI/CD pipelines, or cloud deployments.
- Exposure to enterprise domains such as telecom, BFSI, manufacturing, retail, or public sector.
- Contributions to internal accelerators, reusable components, open-source projects, hackathons, or AI engineering communities.
Why This Role Is Exciting
You will get the opportunity to build agentic AI capabilities for an enterprise-grade platform from an early stage. You will work closely with senior architects and founders, gain exposure to real-world enterprise AI challenges, and contribute directly to the product’s core intelligence layer.
This role offers strong learning, visibility, and ownership. You will not only implement features, but also help shape reusable AI engineering patterns, evaluation practices, and production-grade agent capabilities for a venture-backed Infosys platform.
