Software Engineer – AI Engineering

Job Title: Software Engineer – AI Engineering

About Anblicks

Position Overview

Key Responsibilities

• Develop and maintain full-stack applications, including user interfaces, backend services, REST APIs, and LLM integrations.
• Build AI agent workflows using LLMs, prompt engineering, tool/function calling, and structured outputs.
• Develop and integrate Model Context Protocol (MCP) servers to connect AI agents with enterprise tools, APIs, and data sources.
• Design and enhance RAG pipelines, including data ingestion, chunking, embeddings, vector search, and context retrieval.
• Build secure AI platform capabilities, including access controls, policy enforcement, human approvals, and usage monitoring.
• Integrate enterprise data sources, semantic layers, business glossaries, and knowledge graphs into AI workflows.
• Develop and maintain data pipelines that support AI applications and RAG-based solutions.
• Implement automated testing, LLM evaluations, logging, tracing, and monitoring to ensure application quality and reliability.
• Follow security and privacy best practices, including PII protection, authentication, authorization, and secrets management.
• Collaborate with AI engineers, data engineers, and product teams to deliver scalable solutions.
• Document technical components, troubleshoot production issues, and contribute to reusable libraries and engineering best practices.

Required Qualifications

• Bachelor's degree in Computer Science, Software Engineering, or a related discipline, or equivalent practical experience.
• 4+ years of professional software engineering experience, with strong backend and full-stack development capabilities.
• Proficiency in Python and/or TypeScript/JavaScript with Node.js.
• Experience developing user-facing applications using React, Next.js, or similar frontend frameworks.
• Strong understanding of REST APIs, backend services, and application integration.
• Hands-on experience with LLM APIs such as OpenAI, Anthropic Claude, or Google Gemini, including prompt engineering and tool/function calling.
• Working knowledge of RAG architectures, embedding models, vector databases, and frameworks such as LangChain, LangGraph, or LlamaIndex.
• Experience with SQL, data pipelines, and data platforms such as Snowflake, Databricks, or dbt.
• Familiarity with Git, CI/CD pipelines, Docker, and cloud platforms such as AWS, Azure, or GCP.
• Experience using AI-assisted development tools such as GitHub Copilot, Cursor, Claude Code, or Windsurf.
• Strong analytical, problem-solving, communication, and collaboration skills.

Good to Have

• Experience with MCP and agent development frameworks such as OpenAI Agents SDK, Claude Agent SDK, CrewAI, or AutoGen.
• Exposure to knowledge graphs, ontologies, and semantic technologies such as Neo4j, RDF/SPARQL, or Snowflake Semantic Views.
• Familiarity with LLM evaluation and observability tools such as LangSmith, Langfuse, or Ragas.
• Understanding of authentication and authorization standards, including OAuth 2.0 and OpenID Connect (OIDC).
• Experience with automated testing, application monitoring, distributed systems, and production troubleshooting.
• Contributions to personal AI projects, hackathons, or open-source initiatives involving LLMs, AI agents, or RAG.

What We Offer

• Opportunities to build production-grade Generative AI and agentic AI solutions.
• Exposure to modern AI engineering frameworks, enterprise data platforms, and cloud technologies.
• A collaborative engineering environment focused on innovation, learning, and technical excellence.
• Opportunities to work on impactful projects for global enterprise clients.
• Continuous learning and professional development in emerging AI technologies.