Software Engineer

Software Engineer (LLM & AI Integration) As a Software Engineer specializing in LLM Integration, you’ll be responsible for owning our AI infrastructure, agentic workflows, and the integration of Large Language Models into our core product. You’ll design and implement end-to-end AI features that empower our users and internal teams to leverage generative intelligence. You will maintain a scalable production environment using frameworks like LangChain or LlamaIndex and ensure that model outputs are accurate, secure, and performant. This role is perfect for someone who combines traditional software engineering rigor with a passion for the evolving AI landscape.

What You'll Do AI Infrastructure & LLM Development Design, build, and maintain reliable services that interface with LLMs (OpenAI, Anthropic, or open-source models). Implement Retrieval-Augmented Generation (RAG) pipelines to ground model responses in proprietary data. Build and optimize backend APIs and microservices to support AI-driven features. Develop robust prompt engineering strategies and evaluation frameworks to ensure output quality. Document AI system architecture, model versioning, and integration patterns. Product Integration & Collaboration Collaborate with Product, Design, and Engineering teams to define user-facing AI capabilities. Translate complex business requirements into technical AI solutions (e.g., automated support, intelligent search, or content generation). Optimize model latency and token usage for cost-effective and snappy user experiences. Support front-end teams in delivering seamless AI interactions. Data Engineering for AI Write and optimize SQL queries and vector database schemas (e.g., Pinecone, Weaviate, or Milvus). Implement data preprocessing and embedding pipelines to prepare unstructured data for LLM consumption. Establish best practices for fine-tuning models or managing few-shot learning datasets. Monitoring & AI Ops Monitor LLM performance, \"hallucination\" rates, and API health proactively. Implement guardrails, moderation layers, and validation processes for AI safety. Maintain CI/CD pipelines for AI services and manage model deployments. Stay updated on the latest research in NLP, LLM orchestration, and agentic frameworks.

What You'll Bring 3–5 years of professional experience in Software Engineering, Backend Development, or AI/ML Engineering. Strong Python proficiency, specifically in building scalable backend systems and working with asynchronous programming. Hands-on experience with LLM frameworks such as LangChain, LlamaIndex, or Haystack. Solid understanding of RAG architectures, vector databases, and embedding techniques. Proven ability to work with RESTful APIs and Cloud Infrastructure (AWS, GCP, or Azure). Experience collaborating with cross-functional teams to ship production-grade software features.

Key Skills Problem Solver: Analytical thinker who can debug complex, non-deterministic AI behaviors. Communicator: Excellent skills for explaining technical AI constraints to non-technical stakeholders. Self-Starter: Ability to take ownership of the AI roadmap in a fast-paced environment. Detail-Oriented: Commitment to software craftsmanship, code quality, and AI safety.

Nice to Have Advanced experience with Vector Databases (Pinecone, Chroma, Qdrant). Familiarity with LLM Evaluation tools (Ragas, TruLens, or LangSmith). Experience with deployment orchestration (Docker, Kubernetes, or Serverless functions). Knowledge of fine-tuning techniques and libraries like Hugging Face transformers or peft. Prior work in a startup environment where rapid prototyping and iteration are key.

Why Join Us? You’ll play a critical role in defining our AI strategy from the ground up. We offer a flexible, fully remote work environment where you’ll have the autonomy to choose the best tools for the job and make a massive impact on our product’s evolution. Your work will directly define how our customers interact with the next generation of intelligent software.