Tech Lead

LatentBridge; Maharashtra; On-site; INR 3,000,000 - 5,500,000; Full time

Job summary

LatentBridge is seeking an experienced AI/ML engineering leader to design and deliver GenAI-based solutions. You will own the overall architecture, define AI components, APIs, and data flows, and drive implementation across teams.

You will mentor engineers, collaborate with clients and stakeholders, and guide projects from discovery through production deployment, including security and governance considerations.

Qualifications

• 8–12+ years of software engineering experience.
• 3+ years in AI/ML, GenAI or AI engineering.
• Strong hands-on Python development.
• Experience building GenAI/LLM-based applications.
• Experience with LLMs, prompt engineering, structured outputs and tool/function calling.

Responsibilities

• Understand business requirements and translate them into technical solutions.
• Own architecture and technical design of AI/GenAI solutions.
• Define APIs, data flows, security and deployment approach.
• Lead technical work packages and guide implementation.
• Mentor engineers and ensure best practices.

Skills

Python

GenAI/LLM engineering

Prompt engineering

AI architecture

Solution design

Team leadership

Agile delivery

Client-facing communication

Education

Bachelor's or Master's degree in CS/Engineering

Tools

FastAPI

Flask

Django

REST APIs

Kubernetes

Docker

Azure/AWS/GCP

LangChain

RAG pipelines

Vector databases

Job description

• 8–12+ years of overall software engineering experience
• 3+ years of strong hands‑on experience in AI/ML, GenAI or related AI engineering
• Strong hands‑on Python development
• Strong recent hands‑on experience building GenAI/LLM-based applications
• Strong experience with LLMs, prompt engineering, structured outputs and tool/function calling
• Hands‑on experience with RAG, embeddings, vector databases, document processing, chunking, retrieval and reranking
• Hands‑on experience with AI agents and agent orchestration, including multi‑step workflows, tool‑using agents, memory/state management and human‑in‑the‑loop patterns
• Experience with LangChain, LangGraph, LlamaIndex, Semantic Kernel or similar frameworks
• Good understanding of MCP and emerging standards for connecting AI agents with enterprise systems and tools
• Experience with backend development using FastAPI, Flask, Django or similar frameworks
• Strong understanding of REST APIs, microservices and distributed application architecture
• Experience integrating enterprise applications, databases and third‑party APIs
• Strong coding, debugging, troubleshooting and performance optimisation skills
• Experience owning solution architecture and technical design for enterprise applications
• Experience taking solutions from discovery/prototype through development and production deployment
• Hands‑on exposure to at least one major cloud platform: Azure, AWS or GCP
• Experience with Docker, Kubernetes, CI/CD, cloud‑native application deployment, API management, logging/monitoring and identity/access management
• SQL and relational databases; NoSQL databases; vector databases
• Data ingestion and transformation pipelines; API‑based integration; event‑driven/asynchronous processing
• Understanding of enterprise authentication/authorization, data privacy, PII handling and enterprise security requirements
• Understanding of secure AI architecture, data protection, prompt/input security, AI guardrails, logging, auditability, monitoring, evaluation, regression testing, scalability and cost management
• Experience leading technical teams while continuing to contribute to development
• Strong client‑facing and communication skills
• Experience working in Agile delivery environments
• Ability to move from Client Problem → Solution Architecture → Technical Design → Team Guidance → Hands‑on Coding → Code Review → Deployment → Production Support

Good-to-Have Skills

• Experience with Azure AI Foundry, AWS Bedrock, Google Vertex AI or similar enterprise AI platforms
• Experience with OpenAI, Azure OpenAI, Anthropic Claude, Google Gemini or equivalent models
• Traditional ML/ML engineering knowledge
• LLM evaluation frameworks
• AI guardrails and responsible AI
• LLM observability and tracing
• Model and prompt evaluation
• Token, latency and cost optimisation
• Experience building enterprise AI accelerators or reusable AI platforms
• Experience with multi‑agent or agentic AI solutions
• Experience modernising existing enterprise applications using AI
• Microsoft Fabric or enterprise data platforms
• BFSI, financial services or other regulated enterprise environments
• AI security and responsible AI practices
• Experience supporting technical proposals, estimations and solution presentations
• Experience mentoring engineers and building engineering standards or reusable frameworks
• Git‑based development, branching, pull requests and code reviews
• Experience with API management, secrets/configuration management and production troubleshooting

Key Responsibilities

• Understand business requirements and translate them into the right technical solution
• Own overall architecture and technical design of AI, GenAI and agentic AI solutions
• Define application architecture, AI/LLM components, APIs, integrations, data flows, security and deployment approach
• Evaluate technology and model options based on business need, cost, performance, security and scalability
• Create architecture diagrams, technical design documents, API specifications and implementation guidelines
• Identify technical risks and drive practical solutions
• Actively contribute to coding throughout the project
• Build critical modules, prototypes, reusable components and integrations
• Develop and integrate LLM applications, RAG pipelines, AI agents and APIs
• Support complex coding, integration and performance issues
• Conduct code reviews and ensure good engineering practices
• Improve code quality, performance, security and maintainability
• Lead and guide AI/ML engineers, backend developers and other technical team members
• Break solutions into technical work packages and guide implementation
• Support estimation, sprint planning and technical task allocation
• Track technical progress and address dependencies/blockers
• Mentor team members and improve technical capabilities
• Review designs and code before higher environments
• Ensure technical quality throughout the project
• Work closely with Project Managers, Business Analysts, Solution Architects, QA and DevOps teams
• Own technical delivery and ensure alignment with agreed architecture
• Participate in client discovery and technical workshops
• Understand client landscape, integrations, data, security and infrastructure constraints
• Explain architecture and technical decisions to technical and business stakeholders
• Present solution architecture and technical options during client reviews
• Support pre‑sales with technical solutioning, estimates, architecture and feasibility assessments
• Handle technical questions and challenges during client discussions
• Take AI solutions beyond prototype into production, including security, governance, evaluation, monitoring, scalability, performance and cost management

something around - Anthropic Claude certifications (particularly CCAF for architects), Microsoft AI-103, AWS Certified Generative AI Developer – Professional.

Education / Qualification

• Bachelor's or Master's degree in Computer Science, Engineering, Information Technology or a related discipline
• Equivalent strong hands‑on engineering experience may also be considered