Senior Software Engineer – AI Engineering

Job Title: Senior Software Engineer – AI Engineering Location: Hyderabad, India Experience: 7+ Years Job Type: Full-Time About Anblicks Anblicks is a Great Place to Work® Certified™ Data and AI company that helps enterprises become intelligent, data-driven organizations. We specialize in Data Engineering, Cloud, Analytics, and AI solutions, enabling global businesses to accelerate innovation and digital transformation. Position Overview We are looking for a Senior Software Engineer – AI Engineering to architect and build enterprise-grade AI applications, agentic AI platforms, and LLM-powered solutions. The ideal candidate will have strong full-stack engineering expertise, hands-on experience with LLMs, AI agents, Model Context Protocol (MCP), Retrieval-Augmented Generation (RAG), and enterprise data platforms. In this role, you will take technical ownership of AI capabilities from architecture and design through production deployment, building secure, scalable, and governed AI solutions. You will work across frontend applications, backend services, APIs, data pipelines, and AI integrations while providing technical direction and mentorship to other engineers. This is a hands-on software engineering role focused on production-ready AI applications and agentic systems , rather than traditional Machine Learning or Data Science. Key Responsibilities Own the architecture, design, development, and delivery of AI platform capabilities, taking solutions from prototype to production. Build end-to-end AI applications spanning frontend interfaces, backend services, APIs, data pipelines, and LLM integrations. Design and deploy LLM-powered agents and multi-agent workflows incorporating planning, tool calling, retrieval, and reasoning. Architect secure REST APIs and MCP servers to connect AI agents with enterprise applications, tools, and data sources. Lead the development of RAG pipelines covering document ingestion, chunking, embeddings, vector and hybrid search, reranking, and context assembly. Design governed AI platform capabilities, including agent registries, identity and access controls, policy enforcement, human approvals, usage monitoring, and rollback mechanisms. Integrate enterprise ontologies, taxonomies, business glossaries, knowledge graphs, and semantic layers into AI workflows. Partner with Data Engineering teams to design reliable batch and streaming pipelines, data models, and data contracts supporting AI applications. Develop context engineering frameworks to securely assemble and manage enterprise context across retrieval systems, APIs, semantic layers, memory stores, and tools. Establish LLM testing, evaluation, and observability practices, including response accuracy, groundedness, guardrails, tracing, and audit trails. Implement security and privacy controls covering PII detection and masking, secrets management, and fine-grained data access. Build reusable AI frameworks, SDKs, agent templates, MCP server scaffolds, and RAG components to accelerate engineering delivery. Collaborate with Product, Platform, Data Engineering, and Governance teams to translate business requirements into scalable technical solutions. Mentor engineers, lead architecture discussions and code reviews, and establish engineering best practices. Required Qualifications Bachelor's degree in Computer Science, Software Engineering, or a related field, or equivalent practical experience. 6+ years of professional software engineering experience , including end-to-end ownership of production systems. Strong backend development expertise in Python and/or TypeScript/Node.js using frameworks such as FastAPI, Flask, or Express. Experience building modern frontend applications using React, Next.js, or similar frameworks. Strong expertise in API architecture, development, integration, and security, including REST, GraphQL, webhooks, OAuth 2.0, and OIDC. Hands-on experience developing production-grade LLM applications using models such as OpenAI GPT, Anthropic Claude, Gemini, or Llama, including prompt engineering, tool/function calling, structured outputs, and streaming. Practical experience with RAG architectures and frameworks such as LangChain, LangGraph, or LlamaIndex, and vector search technologies such as pgvector, Pinecone, Weaviate, OpenSearch, or Snowflake Cortex Search. Experience with MCP and agent development frameworks such as OpenAI Agents SDK, Claude Agent SDK, Semantic Kernel, AutoGen, or CrewAI. Strong data engineering and data modeling skills, including SQL, semantic data modeling, and pipelines built using dbt, Airflow, Spark, Snowflake, or Databricks. Experience with cloud platforms such as AWS, Azure, or GCP, along with Docker, Kubernetes, CI/CD, and distributed system design. Proficiency with Git and AI-assisted development tools such as GitHub Copilot, Claude Code, Cursor, or Windsurf, including the ability to guide effective adoption within engineering teams. Strong system design, analytical, troubleshooting, communication, and technical decision-making skills. Ability to mentor engineers and communicate architectural decisions, trade-offs, and risks to technical and business stakeholders. Good to Have Experience with knowledge graphs, ontologies, and semantic technologies such as RDF, OWL, SHACL, SPARQL, Neo4j, or Amazon Neptune. Familiarity with semantic layers such as Snowflake Semantic Views or dbt Semantic Layer. Experience building AI gateways, guardrails, and policy engines using tools such as NeMo Guardrails, Guardrails AI, Open Policy Agent, or Cedar. Knowledge of LLM observability and evaluation tools such as LangSmith, Langfuse, Arize Phoenix, MLflow, Ragas, or OpenTelemetry. Experience delivering software in regulated or highly governed enterprise environments with strict security, audit, and data privacy requirements. Familiarity with data catalog and governance platforms such as Collibra, Alation, Atlan, Unity Catalog, or Snowflake Horizon. Experience with event-driven and streaming architectures such as Kafka or Kinesis, and infrastructure-as-code tools such as Terraform. Demonstrated experience leading platform or product engineering initiatives from concept through production launch. Open-source contributions, technical publications, or personal projects involving agentic AI, MCP, RAG, or AI developer tooling. What We Offer Opportunities to architect and build next-generation Generative AI and agentic AI solutions. Exposure to cutting-edge AI frameworks, enterprise data platforms, and cloud technologies. Technical ownership of impactful AI engineering initiatives for global enterprise clients. A collaborative engineering culture that encourages innovation, continuous learning, and technical excellence. Opportunities to mentor engineers and influence engineering standards and platform architecture. Join Anblicks and help shape the future of enterprise AI through secure, scalable, and intelligent software engineering.