SENIOR AI DEVELOPER

Art Technology and Software

Website: artechsoft.com
Job details:

We are seeking a Senior AI Developer who thrives at the intersection of software engineering and applied AI. You will design, build, and optimise LLM-powered features, AI agent pipelines, and RAG systems that are reliable, scalable, and production-ready. With 8+ years of engineering experience and 3+ years focused on AI agent and LLM development, you bring both depth and versatility — moving fluidly between system design, hands-on coding, and cross-team collaboration.

KEY RESPONSIBILITIES

AI Feature Development

▸ Design, develop, and ship LLM-powered features including conversational agents, document intelligence, and automated decision-support tools.

▸ Build and maintain production-grade RAG pipelines — document ingestion, chunking, embedding, vector retrieval, re-ranking, and context injection.

▸ Develop and iterate on prompt engineering artefacts: system prompts, few-shot templates, chain-of-thought strategies, and structured output schemas.

▸ Implement and test AI agent workflows using frameworks such as LangGraph, LangChain, AutoGen, or CrewAI.

Engineering Quality & Delivery

▸ Drive the use of agentic coding tools (Claude Code, Cursor, GitHub Copilot, or equivalent) to automate and accelerate the software delivery lifecycle — translating PRDs and technical specs into working code, conducting AI-assisted code reviews, generating test cases, and enforcing quality criteria across the output.

▸ Expected to define and maintain quality standards for AI-generated code and continuously improve agentic workflows as tooling evolves.

▸ Build LLM evaluation harnesses (Evals, RAGAS, TruLens, PromptFoo) to measure output quality, regression, and safety across model updates.

▸ Implement observability for AI systems: latency tracking, token usage monitoring, drift detection, and user feedback integration.

▸ Participate actively in code reviews, technical design discussions, and sprint planning.

Model & Platform Integration

▸ Integrate with LLM APIs (OpenAI, Anthropic Claude, Google Gemini, Cohere, HuggingFace) and select the right model per use case.

▸ Work with vector databases (Pinecone, Weaviate, pgvector, Qdrant, Chroma) and optimise retrieval performance at scale.

▸ Support fine-tuning workflows using SFT, LoRA, QLoRA, or PEFT where required for domain-specific performance.

▸ Integrate AI components with enterprise APIs, data pipelines, and third-party platforms including fintech and payments ecosystems.

Collaboration & Knowledge Sharing

▸ Collaborate closely with the Tech Lead, Product Managers, QA, and Prompt Engineers to translate requirements into shipped AI features.

▸ Document technical decisions, architecture choices, and model evaluation results clearly for team and stakeholder consumption.

▸ Mentor junior developers on AI best practices, responsible AI principles, and engineering standards.

REQUIRED QUALIFICATIONS

Experience & Education

▸ 8+ years of overall software engineering experience with a strong backend and API design foundation.

▸ 3+ years of focused, hands-on experience building and deploying AI agent systems, LLM-powered applications, and RAG pipelines in production.

▸ Demonstrable experience with LLM-based and agentic solution implementation in real-world, at-scale environments.

▸ Bachelor's or Master's degree in Computer Science, AI/ML, Software Engineering, or equivalent practical expertise.

Technical Skills

▸ Deep expertise in RAG architecture: chunking, embeddings, vector search, hybrid retrieval, document parsing, Evals, and SFT (Supervised Fine-Tuning).

▸ LLM API proficiency: OpenAI, Anthropic (Claude), Google Gemini, Cohere, and open-source models via HuggingFace / Ollama.

▸ Agentic frameworks: LangChain, LangGraph, AutoGen, CrewAI, Semantic Kernel, or equivalent.

▸ Strong Python engineering — async programming, packaging, testing, and production-grade code standards.

▸ Vector databases: Pinecone, Weaviate, Milvus, pgvector, Qdrant, or Chroma.

▸ Cloud & DevOps: AWS / Azure / GCP, Docker, Kubernetes, CI/CD pipelines.

▸ Data engineering: ETL pipelines, SQL/NoSQL databases, streaming platforms (Kafka / Pub-Sub).

PREFERRED QUALIFICATIONS

▸ Experience in fintech, payments, or regulated industries — familiarity with compliance, data residency, and auditability requirements.

▸ Hands-on fine-tuning experience: LoRA, QLoRA, PEFT, or RLHF workflows.

▸ Familiarity with AI evaluation frameworks: RAGAS, TruLens, PromptFoo, or custom eval harnesses.

▸ Exposure to multi-modal AI inputs (text, documents, structured data) in production systems.

▸ Open-source contributions or published technical writing in the AI/ML space.

CORE COMPETENCIES

🔨 Builder Mindset

Ships clean, well-tested, production-ready AI systems — not just prototypes.

🧠 Deep Technical Ownership

Takes end-to-end ownership of features from architecture through deployment and monitoring.

🔬 Curious Experimenter

Evaluates new models, frameworks, and techniques — and knows when to adopt vs. wait.

🤝 Strong Collaborator

Works closely with PM, QA, and design; communicates technical decisions clearly.

📐 Quality-First

Writes robust, maintainable code with LLM evals, unit tests, and observability built in.

🛡️ Responsible AI

Applies guardrails, safety layers, and hallucination mitigation as default practice.

Click on Apply to know more.