Overview
GenAI Application Engineer – Chennai
Build intelligent systems that think, reason, and evolve.
Location: Chennai, India
Experience: 3–6 years in software engineering, with 1.5–3 years in GenAI application development.
Engineers who go beyond coding — to design and deliver AI-powered applications that redefine enterprise intelligence.
Role Overview
As a GenAI Application Engineer, you’ll design, build, and scale next-generation AI applications that leverage large language models, retrieval systems, and agentic frameworks. You’ll collaborate closely with product, infrastructure, and data teams to embed intelligent, secure, and reliable GenAI capabilities across the organization. This role sits at the intersection of AI innovation, system design, and operational excellence — ideal for engineers who love solving real-world problems with cutting-edge AI.
GenAI Application Development – Design and develop scalable GenAI applications integrating LLMs, embeddings, and agentic frameworks.
Retrieval-Augmented Generation (RAG) – Build contextual retrieval pipelines with vector databases like Chroma, Pinecone, or Weaviate.
AI Orchestration & Frameworks – Architect GenAI services using LangChain, LangGraph, or CrewAI, leveraging APIs from OpenAI, Anthropic, or Mistral.
Reliability & Observability – Implement tracing, logging, and fault-tolerant systems aligned with SRE principles.
Evaluation & Guardrails – Monitor and optimize model behavior, latency, token cost, and content safety.
Automation & CI/CD – Develop and automate MLOps pipelines for deployment, versioning, and continuous integration of AI services.
Cross-Functional Collaboration – Partner with product, infra, and data teams to ensure governance, compliance, and scalable delivery of AI features.
Proficient in Python (FastAPI/Flask) with strong grounding in software design patterns, concurrency, and microservices.
Hands-on with LangChain, LangGraph, or CrewAI, and familiar with agentic workflows.
Experienced in RAG systems, embeddings, and vector store integration.
Skilled in cloud deployment (AWS ECS/Lambda, Azure Functions, or GCP Cloud Run) and Infrastructure as Code (Terraform, CloudFormation).
Strong understanding of system performance tuning, including caching, rate limiting, and load balancing.
Familiar with APIs (REST/GraphQL), databases (SQL/NoSQL), and event-driven systems (Kafka, Pub/Sub).
Experience with observability and security tooling — OpenTelemetry, Prometheus, Guardrails, RBAC, and API gateway policies.
Systems Thinker – You see the end-to-end flow and optimize for performance and scalability.
Structured & Adaptable – You thrive in evolving GenAI frameworks and dynamic environments.
Proactive Collaborator – You bridge engineering, product, and AI disciplines seamlessly.
Continuous Learner – You stay curious, experiment boldly, and never stop iterating.
Python | FastAPI | LangChain | LangGraph | CrewAI | AWS | GCP | Azure | Terraform | Prometheus | OpenTelemetry | Kafka | SQL | NoSQL