Python Tech Lead
- Full-time
Company Description
About Sutherland
Artificial Intelligence. Automation.Cloud engineering. Advanced analytics.For business leaders, these are key factors of success. For us, they’re our core expertise.
We work with iconic brands worldwide. We bring them a unique value proposition through market-leading technology and business process excellence.
We’ve created over 200 unique inventions under several patents across AI and other critical technologies. Leveraging our advanced products and platforms, we drive digital transformation, optimize critical business operations, reinvent experiences, and pioneer new solutions, all provided through a seamless “as a service” model.
For each company, we provide new keys for their businesses, the people they work with, and the customers they serve. We tailor proven and rapid formulas, to fit their unique DNA.We bring together human expertise and artificial intelligence to develop digital chemistry. This unlocks new possibilities, transformative outcomes and enduring relationships.
Sutherland
Unlocking digital performance. Delivering measurable results.
Job Description
We are seeking an experienced Python Tech Lead / Associate Manager to lead our AI development initiatives, with deep expertise in building production-grade agentic AI systems using LangChain, LangGraph, and related frameworks. This role combines technical leadership with hands-on development, requiring someone who can architect complex AI solutions while mentoring a team of developers.
Key Responsibilities
Technical Leadership
- Architect and design scalable agentic AI systems using LangChain and LangGraph frameworks
- Lead the development of autonomous AI agents with multi-step reasoning and decision-making capabilities
- Establish best practices for prompt engineering, agent orchestration, and AI system reliability
- Drive technical decisions on framework selection, tool integration, and system architecture
- Conduct code reviews and ensure high-quality, maintainable codebases
Hands-on Development
- Build complex agent workflows using LangGraph's state machines and conditional logic
- Implement multi-agent systems with tool calling, memory management, and retrieval mechanisms
- Develop custom chains, agents, and tools within the LangChain ecosystem
- Optimize LLM performance through prompt tuning, caching strategies, and efficient API usage
- Integrate vector databases, embeddings, and retrieval-augmented generation (RAG) pipelines
Team Management
- Mentor and guide a team of 3-7 developers in AI/ML development practices
- Facilitate knowledge sharing sessions on agentic AI patterns and emerging technologies
- Coordinate sprint planning, task allocation, and delivery timelines
- Foster a culture of innovation and continuous learning within the team
Qualifications
Core Python & AI Frameworks
- 6+ years of Python development experience with strong expertise in async programming, type hints, and modern Python patterns
- 2+ years hands-on experience with LangChain and LangGraph building production applications
- Deep understanding of agentic AI architectures including ReAct, Plan-and-Execute, and Reflection patterns
- Experience with LangChain Expression Language (LCEL) for chain composition
- Experience with developing and maintaining FastAPI projects with React Framework.
Agentic AI Specific Modules
- LangGraph: StateGraph, MessageGraph, conditional edges, human-in-the-loop patterns, checkpointing and persistence
- LangChain Core: Agents (OpenAI Functions, Structured Chat, ReAct), Tools, Toolkits, Memory systems (ConversationBufferMemory, ConversationSummaryMemory, VectorStoreMemory)
- LangChain Callbacks: Custom callback handlers, tracing, logging, and observability
- Agent Executors: AgentExecutor configuration, error handling, and timeout management
- Multi-Agent Systems: Agent coordination, communication protocols, task delegation
LLM & Model Integration
- Experience with OpenAI GPT-4/GPT-3.5, Anthropic Claude, or open-source models (Llama, Mistral)
- Understanding of model selection, cost optimization, and fallback strategies
- Prompt engineering expertise including few-shot learning, chain-of-thought prompting
- Experience with function calling and structured outputs from LLMs
Vector Databases & Retrieval
- Hands-on experience with vector databases: Pinecone, Weaviate, Chroma, or FAISS
- Implementation of RAG pipelines with document chunking, embedding generation, and similarity search
- Knowledge of semantic search, hybrid search, and re-ranking techniques
- Experience with embedding models (OpenAI embeddings, Sentence Transformers, Cohere)
Additional AI/ML Frameworks
- LlamaIndex for advanced data indexing and querying
- Haystack or Semantic Kernel as alternative orchestration frameworks
- Hugging Face Transformers for custom model integration
- MLflow or Weights & Biases for experiment tracking
Data & Integration
- API integration experience (REST, GraphQL, webhooks), Frameworks : FastApi
- Document processing: PDF parsing, OCR, web scraping (Beautiful Soup, Scrapy)
- Database expertise: PostgreSQL, MongoDB, Redis for caching and session management
- Message queues: RabbitMQ, Kafka for asynchronous agent communication
DevOps & Production
- Docker and Kubernetes for containerization and orchestration
- CI/CD pipelines (Azure Devops, GitHub Actions, GitLab CI, Jenkins, Azure Devops)
- Cloud platforms: AWS (Lambda, ECS, SageMaker), GCP, or Azure
- Monitoring and observability: LangSmith, Prometheus, Grafana, or Datadog
- Experience with LLM observability tools: Helicone, LangSmith, or Weights & Biases
Desired Qualifications
- Bachelor's or Master's degree in Computer Science, Engineering, or related field
- Experience building production AI applications with measurable business impact
- Strong understanding of software design patterns and clean architecture principles
- Familiarity with testing frameworks for AI systems (pytest, unit testing for agents)
- Knowledge of security best practices for AI applications (prompt injection prevention, PII handling)
- Experience with streaming responses and real-time agent interactions
- Understanding of token optimization and cost management strategies
- Previous experience in a tech lead or team lead capacity
Soft Skills
- Excellent problem-solving abilities with a systematic approach to debugging complex agent behaviors
- Strong communication skills to explain technical concepts to non-technical stakeholders
- Ability to balance technical excellence with practical business needs
- Collaborative mindset with experience working in cross-functional teams
- Adaptability to rapidly evolving AI technologies and frameworks
Nice to Have
- Contributions to open-source AI projects or LangChain ecosystem
- Experience with fine-tuning LLMs or building custom models
- Knowledge of AI safety, alignment, and responsible AI practices
- Experience with graph databases (Neo4j) for knowledge graph applications
- Familiarity with AutoGPT, BabyAGI, or similar autonomous agent frameworks
- Understanding of reinforcement learning from human feedback (RLHF)
What We Offer
- Opportunity to work on cutting-edge AI technologies
- Collaborative and innovative work environment
- Professional development and conference attendance support
- Competitive salary and benefits package
- Flexible work arrangements
Location: [Chennai]
Experience Level: 6-10 years
Team Size: Leading a team of 3-7 developers
By clicking the link above or any third-party link within this posting, you are leaving this site and going to a third-party website where the third-party website's terms and privacy policy apply