Architect and build production-grade generative AI and agentic AI applications, including LLM workflows, multi-agent systems, RAG pipelines, APIs, and ML/GenAI infrastructure. Develop and optimize models, manage deployment and monitoring, apply responsible AI practices, and collaborate directly with customers. The role also involves mentoring engineers and shaping AI platform strategy.
This role is for one of Weekday’s clients
Min Experience: 5+ years
Location: Remote (India)
JobType: full-time
We're looking for a Senior Agentic AI/Generative AI Engineer to help architect our next-generation AI-driven products — from prototyping through production deployment. This is a customer-facing role where you'll move fluidly between solution architecture, hands-on engineering, and client conversations.
Requirements
Key Responsibilities:
- Architect and build scalable Generative AI and agentic AI applications, end to end
- Design LLM-powered workflows and prompt strategies for reflexive, self-learning, multi-agent systems
- Build intelligent AI agents using LangChain and LangGraph for use cases like NL-to-SQL, autonomous task agents, and RAG pipelines
- Select, customize, fine-tune, and optimize state-of-the-art LLMs
- Design and own full ML/GenAI pipelines — training, deployment, monitoring, lifecycle management
- Build APIs, microservices, and integration frameworks to bring AI into enterprise products
- Champion responsible AI practices — mitigating hallucinations, bias, and reliability risks
- Partner directly with customers, product, and engineering to turn business needs into robust AI architecture
- Mentor engineers and help shape our long-term AI platform strategy
Required Qualifications:
- 6+ years in traditional ML, including 2+ years hands-on with Generative AI
- Strong experience with LLMs (GPT and similar), prompt engineering, and agentic systems
- Real-world experience with LangChain/LangGraph or similar agentic frameworks
- Strong Python skills — API wrappers, third-party integrations, internal tooling
- Solid foundation in Transformers, CNNs, RNNs — hands-on with TensorFlow, PyTorch, Scikit-learn
- Experience with NLP, embedding models, and vector databases
- Hands-on work with OpenAI, Llama/Llama2, Azure OpenAI, and other open-source models
- Experience designing distributed, cloud-native architectures (microservices, REST APIs)
- Proficiency with AWS, Azure, or GCP, plus Docker/Kubernetes
- MLOps/LLMOps experience — training, deployment, monitoring, lifecycle management
- Excellent communication skills — you can translate technical depth for non-technical stakeholders
- Bachelor's or Master's in CS, Data Science, Engineering, Math, Statistics, or related field
- Comfort with startup pace and strong ownership mentality
Preferred Qualifications:
- LLM fine-tuning experience (LoRA, RLHF, PEFT)
- Performance optimization (GPU/TPU acceleration, quantization, pruning, distillation)
- AI observability/monitoring tool experience
- Familiarity with AI governance and compliance (GDPR, SOC 2)
- Prior consulting or solution-architecture experience shipping enterprise AI products
- Background in financial services, healthcare, or insurance
Must-have skills
Agentic AI, Generative AI, Artificial Intelligence
Good-to-have skills
Machine Learning, LangChain, LangGraph
Similar Jobs
Pharmaceutical
Build and productionize generative AI agents and workflows for Patient Services in a regulated healthcare environment. Develop RAG pipelines, vector retrieval systems, MCP integrations, evaluation harnesses, and reusable prompt and agent patterns. Integrate AI capabilities with Salesforce Health Cloud, MuleSoft, and Java systems. Own the full agent lifecycle, including deployment, monitoring, evaluation, cost and latency optimization, and retirement. Collaborate within a follow-the-sun engineering model.
Top Skills:
ApexBigQueryClaude ApiClaude CodeCrewaiCursorDataweaveGCPGemini Enterprise ApiGithub CopilotGraphQLJavaJavaScriptLangchainLanggraphLightning Web ComponentsModel Context ProtocolMulesoftPostgresPythonRestSalesforce Health CloudTypescriptVector DatabasesVertex AiVertex Ai Agent Builder
Artificial Intelligence • Fintech • Software • Financial Services
Build agent capabilities for AI phones, including workflow orchestration, tool integrations, context retrieval, memory, multi-step execution, long-running stateful workflows, and reliability improvements. Integrate local and cloud model providers, develop evaluation and regression tests, and support production AI infrastructure. The role requires backend or AI application engineering expertise, programming proficiency, LLM API and tool-calling experience, and knowledge of APIs, distributed systems, state management, and asynchronous execution.
Top Skills:
Api IntegrationsAsynchronous ExecutionDistributed SystemsGoLlm ApisModel RoutingPythonRagTypescript
Database • Analytics
Lead the architecture and development of production-grade agentic AI systems and AI-augmented software development workflows. Build multi-agent applications, orchestration, tool integrations, RAG systems, APIs, and cloud-native services. Establish evaluation frameworks, quality gates, observability, security, and guardrails for autonomous systems. Provide technical leadership, mentor engineers, evaluate emerging AI coding tools, and guide adoption of agentic engineering practices across the software development lifecycle.
Top Skills:
Arize PhoenixAutogenAWSAzureCi/CdClaude CodeCrewaiDockerFastapiGCPGoogle AdkHermes AgentKubernetesLangchainLangfuseLanggraphMcpOpentelemetryPiPythonRagSemantic SearchVector Retrieval
What you need to know about the Chennai Tech Scene
To locals, it's no secret that South India is leading the charge in big data infrastructure. While the environmental impact of data centers has long been a concern, emerging hubs like Chennai are favored by companies seeking ready access to renewable energy resources, which provide more sustainable and cost-effective solutions. As a result, Chennai, along with neighboring Bengaluru and Hyderabad, is poised for significant growth, with a projected 65 percent increase in data center capacity over the next decade.
