Senior Gen AI Developer

About the Company GoodHiresOnly is hiring for a client a Global IT Services headquartered in the UK , operating internationally at the forefront of digital transformation and next-generation engineering services. The company specializes in DevOps, Cloud, Integration, Automation, and Low Code Application Development, delivering innovative solutions to help organizations build digital-first strategies and streamline business processes. Job Overview We are seeking an experienced Senior Gen AI Developer to join the team to build and enhance core services and capabilities on an enterprise-grade Generative AI platform for a Global Insurance Company (Aviva, UK) . This role blends strong P ython backend engineering with DevOps enablement and hands-on integration of Large Language Models (LLMs) within secure, scalable enterprise environments. The ideal candidate will bring a deep practical understanding of GenAI development , strong automation skills, and a passion for solving emerging engineering challenges in this rapidly evolving field. Key Aspects Salary Budget – INR 30-35 LPA Onsite Allowance (UK) – GBP 75/ Day (per diem) plus flights, visa, and initial (2 weeks) accommodation. Onsite Project Opportunity – Aviva, Hoxton Square, London (Hybrid model) Base Locations – Chennai, Hyderabad, Pune, or Bangalore (Hybrid model) Experience – Minimum 7+ years in software development, with at least 3 years in Gen AI development Reporting – Client and Project Manager, UK Job Type – Full-Time, Permanent Employment Notice Period – Less than 45 days Role Summary As a Senior Gen AI Developer, you will collaborate with cross-functional teams, including platform leads, architects, and Site Reliability Engineers (SREs). You will design, develop, integrate, and optimize Python-based GenAI services and APIs that enable secure access to LLM capabilities in enterprise cloud environments. Your role will also involve benchmarking, evaluation, and automation to improve service reliability and cost-efficiency, while ensuring compliance with regulated industry security standards. Key Responsibilities Architect, build, and maintain backend services and APIs enabling secure integration with LLMs. Develop and optimize Python-based GenAI components including prompt orchestration, output validation, and evaluation tooling. Integrate LLMs with enterprise systems, observability, and security frameworks. Design and maintain CI/CD pipelines primarily on Azure DevOps aligned with modern engineering and DevOps standards. Collaborate closely across teams to ensure the reliable operationalization of GenAI services. Support benchmarking, experiment tracking, and cost-performance evaluation of LLMs. Contribute to Retrieval-Augmented Generation (RAG) implementations and data access patterns for enterprise use cases. Help shape API standards, reusable patterns, and documentation to support platform adoption. Troubleshoot and optimize performance of distributed systems and cloud services. Mandatory Skills & Experience Strong Python backend engineering expertise in production systems with frameworks like Django. Working knowledge of generative AI technologies and Large Language Models. Experience in evaluating LLM performance and managing prompt complexities. Solid DevOps mindset with CI/CD expertise and observability best practices; experience with Azure DevOps preferred. Proven ability to work securely in regulated enterprise environments with strict security controls. Experience integrating AI services into practical applications or workflows. Familiarity with authentication, secret management, network boundaries, and model access governance. Preferred Skills Experience with Kong API Gateway, Kong Mesh, and Flux CD. AWS cloud services including EC2, EKS, S3, SQS, DynamoDB, Bedrock. RESTful API development with FastAPI preferred, microservices architecture, Infrastructure as Code using Terraform and GitOps workflows. Familiarity with prompt evaluation tools such as Promptfoo. Experience with SQL (MySQL, PostgreSQL) and NoSQL (MongoDB, Cassandra) databases. Exposure to RAG patterns and vector search technologies. Behavioural Competencies Proactive self-starter who identifies gaps and drives solutions without waiting for detailed instructions. Comfortable operating in ambiguous, evolving domains where best practices are still emerging. Collaborative communicator capable of influencing and gaining trust across engineering, data, and product teams. Curiosity and passion for exploring and adopting new GenAI techniques in a structured, secure manner. Strong bias toward automating repetitive tasks to reduce toil and accelerate delivery. What Success Looks Like Delivery of efficient, secure, and reusable GenAI components into production. Improved engineering velocity through automation and DevOps excellence. Stable services equipped with observability and rigorous evaluation from day one. Positive feedback and adoption from platform and application teams. Clear, concise documentation enabling fast onboarding and future scalability. Why Join Us Opportunity to work on cutting-edge GenAI projects at a global Insurance company International exposure with onsite opportunity in London Collaborate within a Great Place to Work (GPTW) certified environment Access to continuous learning, mentoring opportunities, and career advancement Hybrid work model ensuring work-life balance and flexibility Note: This job description outlines general responsibilities and qualifications and is not exhaustive. For further queries, contact