Fullstack AI/ML Developer

Role Overview: Full Stack Engineer

As an Full Stack Engineer within the Digital department, you will be responsible for designing, building, and deploying advanced AI solutions. These include chatbots, intelligent agents, and agentic workflows that utilize state-of-the-art large language model (LLM) APIs such as OpenAI, Anthropic, and Google Gemini. Your work will involve integrating retrieval-augmented generation (RAG), multimodal LLMs, and document understanding to address real-world challenges in renewable energy and industrial settings. Additionally, you will be tasked with training and deploying classical machine learning models that predict events and identify root causes of failures in factory environments.

Key Responsibilities

• Conversational AI & Agent Orchestration: Develop robust chatbots and agentic systems using LLMs (OpenAI, Anthropic, Gemini). Implement retrieval-augmented generation (RAG), vector search, and multimodal pipelines to deliver reliable, high-quality user experiences.
• Backend APIs & Model Serving: Deploy production-grade APIs and web services that serve ML/LLM models and chatbots utilizing FastAPI or Node/Express. Implement OpenAPI/Swagger, OAuth/OIDC authentication, and pagination.
• Frontend UX: Create lightweight front ends using modern frameworks (React, Next.js, Angular, or Streamlit) to demo, operate, and monitor AI features, including dashboards, chat user interfaces, forms, and simple admin tools.
• Document Intelligence & Multimodal Extraction: Build tools for multimodal extraction and analysis of complex documents such as PDFs and engineering drawings (P&IDs, electrical schematics), delivering structured and actionable outputs.
• Cloud DevOps & Productionization: Deploy solutions to production using CI/CD practices, containerize services, and integrate with data sources and enterprise systems. Ensure reliability, scalability, and cost efficiency.
• MLOps Observability & Quality: Monitor latency, accuracy, and cost metrics. Implement observability, prompt/response logging, evaluations, and automated regressions to maintain high quality.

Model Tuning, Training & Evaluation: Fine-tune and perform few-shot learning with LLMs, train supporting models (classification, OCR, extraction), build datasets, conduct experiments, compare checkpoints, and document results.

Required Skills

• At least 1 year of hands-on experience building and deploying generative AI products such as chatbots, agents, or agentic workflows
• Minimum 4 years of professional software engineering experience
• Bachelor's degree in Computer Science, Statistics, or a related field
• Strong proficiency in Python and experience with OpenAI, Anthropic, or Google Gemini APIs
• Proven ability to develop production APIs and web services using FastAPI, Flask, Django, or Node/Express
• Working knowledge of front-end fundamentals (HTML, CSS, JavaScript) and experience with at least one modern framework (React, Next.js, Angular, or Vue) for delivering basic UIs
• Solid foundation in software engineering best practices including Git, code review, testing, CI/CD, and experience with cloud platforms (AWS, GCP, Azure)
• Strong communication skills and ability to address open-ended, ambiguous problems

Preferred Skills

• PhD or Master's degree in Computer Science, Statistics, or a related field
• Over 2 years of industrial experience in Generative AI and Machine Learning
• Experience with LangChain, LlamaIndex, orchestration frameworks, and tool-use/agents
• Practical expertise in retrieval-augmented generation (RAG), embeddings, and vector databases (such as FAISS, Pinecone, Weaviate, pgvector)
• Familiarity with industrial control systems, including PLCs and SCADA
• Experience in renewable energy, manufacturing, or industrial automation sectors
• Knowledge of MLOps practices including Docker/Kubernetes, model packaging, feature/vector stores, evaluations, tracing/observability

(OpenTelemetry), and A/B testing

Technology Stack

• FastAPI
• Express
• React/Next.js
• Angular
• PostgreSQL
• AWS
• Docker
• Bitbucket Pipelines