Tech Lead - Agentic AI

Experience Required
8+ years of enterprise software engineering experience
3+ years of microservices / backend platform development experience
Exposure to AI / LLM / RAG-based applications preferred, but not mandatory
EDUCATIONAL REQUIREMENTS
• Bachelor’s or Master’s degree in Computer Science, Information Technology,
Artificial Intelligence, or a related fielRequired Skills
• Strong experience in enterprise backend application development.
• Good experience designing and building microservices-based applications.
• Hands-on experience with Java / Spring Boot, Python / FastAPI, Node.js, .NET, or
similar backend frameworks.
• Strong understanding of REST APIs, service contracts, JSON, authentication,
authorization, and integration patterns.
• Experience with relational databases such as PostgreSQL, MySQL, SQL Server, or
Oracle.
• Experience with cloud platforms such as AWS, Azure, or GCP.
• Experience with Docker and container-based application deployment.
• Understanding of event-driven architecture using SQS, Kafka, RabbitMQ,
EventBridge, Step Functions, or similar tools.
• Good understanding of logging, monitoring, error handling, retry logic, performance
tuning, and production support.
• Strong problem-solving ability and comfort working on complex enterprise
workflows.
Key Responsibilities
• Design and develop enterprise-grade backend services and microservices.
• Build APIs, service interfaces, workflow components, and integration layers.
• Develop reusable services for orchestration, data processing, search,
recommendation, classification, summarization, and decision-support workflows.
• Work with AI / LLM services to support prompt-based processing, structured
outputs, reasoning flows, and recommendation generation.
• Support RAG-style workflows using knowledge sources, embeddings, semantic
search, and vector databases where required.
• Implement event-driven processing using queues, schedulers, workflow engines, or
messaging services.
• Design and manage data models, service contracts, JSON schemas, audit logs, and
output structures.
• Collaborate with DevOps teams for containerized deployment, CI/CD, monitoring,
and environment promotion.
• Ensure services are scalable, secure, maintainable, traceable, and productionready.
• Work with QA, validation, business, and domain teams to support testing, release
readiness, and controlled changes.
• Troubleshoot application, integration, performance, and production issues.
AI / LLM Skills Preferred
• Exposure to LLM-based application development using OpenAI, Azure OpenAI, AWS
Bedrock, Anthropic, Llama, or similar platforms.
• Understanding of prompt engineering, structured outputs, confidence scoring, and
response validation.
• Experience with RAG, embeddings, vector search, semantic search, or knowledge
retrieval.
• Familiarity with LangChain, LangGraph, LlamaIndex, Semantic Kernel, CrewAI,
AutoGen, or similar frameworks is useful but not mandatory.
• Ability to work with AI engineers / data scientists to integrate models, prompts,
retrieval pipelines, and recommendation logic into enterprise applications.
Good-to-Have Skills
• Experience building platforms in healthcare, pharma, medical devices, quality,
compliance, insurance, banking, or other regulated industries.
• Experience with human-in-the-loop workflows, review queues, approval flows, audit
trails, and controlled release processes.
• Exposure to search platforms such as OpenSearch, Elasticsearch, pgvector,
Pinecone, Weaviate, FAISS, or similar.
• Experience with AWS services such as ECS, Lambda, RDS / Aurora, S3,
OpenSearch, EventBridge, SQS, Step Functions, Secrets Manager, and CloudWatch.
• Exposure to AI agents, orchestration flows, classification engines, decision-support
systems, or recommendation platforms.
• Understanding of validation, traceability, audit evidence, and enterprise release
governance.
Expected Deliverables
• Microservice design and implementation.
• API design, service contracts, and integration components.
• Backend services for orchestration, processing, recommendation, classification,
and summarization.
• AI / LLM integration components.
• RAG / search / retrieval service integration where required.
• Database models, schemas, and persistence logic.
• Event-driven workflow components.
• Unit tests, integration tests, and technical documentation.
• Deployment-ready services with logging, monitoring, and error handling.
• Support for release readiness, defect resolution, and production stabilization.

Work arrangement
Yes