Senior AI Engineer
GenAI · Conversational AI · Voice & Chat Bots · LLM Integration · Solution Architecture
ABOUT THE ROLE
- We are a data and AI services firm seeking a Senior AI Engineer to lead the design and delivery of intelligent,
- conversational, and agentic AI solutions for our clients. This is a hands-on, client-facing engineering role — you
- will architect and build production-grade GenAI applications, voice and chat bots, and LLM-powered integrations
- across a variety of industries and technology stacks.
- You will be the technical authority on AI engagements — owning solution architecture, driving LLM selection and
- fine-tuning decisions, and integrating AI capabilities into existing client systems. You will work closely with clients
- through presales, discovery, and delivery, and will mentor junior engineers within the Data Practice.
KEY RESPONSIBILITIES
Conversational AI — Chat & Voice Bots
▸ Design and deliver production-ready chatbots and voicebots for client-facing and internal enterprise use
cases.
▸ Build real-time voice AI pipelines using LiveKit — handling audio streaming, VAD (voice activity detection),
STT/TTS integration, and turn management.
▸ Architect multi-turn, context-aware conversational flows with robust fallback handling and session state
management.
▸ Integrate speech-to-text (Whisper, Azure Speech, Deepgram) and text-to-speech (ElevenLabs, Azure TTS,
OpenAI TTS) providers based on client requirements.
▸ Ensure low-latency, high-availability voice and chat deployments suitable for customer-facing production
traffic.
LLM Integration & Orchestration
▸ Build LLM-powered applications using LangChain, LangGraph, and LlamaIndex — including RAG
pipelines, agents, and tool-calling workflows.
▸ Integrate OpenAI, Azure OpenAI, Anthropic Claude, Google Gemini, and open-source models (Llama,
Mistral, Phi) based on cost, latency, and compliance needs.
▸ Design and implement Retrieval-Augmented Generation (RAG) systems with vector stores (Pinecone,
Weaviate, pgvector, Azure AI Search).
▸ Build and manage AI agent frameworks — autonomous agents, multi-agent workflows, and human-in-the loop patterns.
▸ Develop prompt engineering strategies, prompt templates, and evaluation pipelines for consistent, reliable
LLM output.
Fine-Tuning & Model Customisation
▸ Fine-tune open-source LLMs (Llama 3, Mistral, Phi-3) using techniques such as LoRA, QLoRA, and PEFT
for domain-specific use cases.
▸ Manage fine-tuning pipelines end-to-end — dataset curation, preprocessing, training, evaluation, and
model registry management.
▸ Implement RLHF / DPO alignment techniques where applicable to align model outputs with client
expectations.
▸ Benchmark model performance using standardised and custom evaluation suites; iterate based on results.
Solution Architecture & Client Engagement
▸ Own AI solution architecture for client engagements — selecting the right models, frameworks, and
infrastructure patterns for each use case.
▸ Participate in presales — contribute to proposals, solution briefs, PoCs, and effort estimations for AI
projects.
▸ Lead client discovery sessions, translating ambiguous business requirements into concrete, executable AI
solution designs.
▸ Present architecture decisions and technical recommendations clearly to both technical and non-technical
client stakeholders.
▸ Handle multiple client engagements simultaneously, managing delivery timelines and technical quality
across projects.
Integration & Production Engineering
▸ Integrate AI capabilities into client systems via REST APIs, webhooks, and event-driven architectures.
▸ Deploy AI services on cloud platforms (Azure, AWS, GCP) using containerised (Docker, Kubernetes) and
serverless patterns.
▸ Implement observability for AI systems — tracing, logging, hallucination detection, and LLM performance
monitoring (LangSmith, Arize, Helicone).
▸ Ensure AI systems meet security, compliance, and data privacy standards — including PII handling, data
residency, and responsible AI guardrails.
▸ Build CI/CD pipelines for model deployment, versioning, and rollback in production environments.
Mentorship & Practice Development
▸ Mentor junior and mid-level AI engineers, conducting code reviews and guiding best practices in LLM
application development.
▸ Contribute to internal AI accelerators, reusable templates, and knowledge-sharing initiatives within the
practice.
▸ Stay current with rapidly evolving GenAI research and tooling; evaluate and advocate for adoption of
relevant advances.
REQUIRED SKILLS & TECHNOLOGIES
Python LangChain / LangGraph LlamaIndex
LiveKit OpenAI / Azure OpenAI Anthropic Claude
RAG Pipelines Vector Databases LLM Fine-Tuning (LoRA / QLoRA)
Prompt Engineering AI Agents & Orchestration Chat Bot Development
Voice Bot Development STT / TTS Integration REST API Integration
Docker / Kubernetes Azure / AWS / GCP Solution Architecture
Hugging Face Transformers Responsible AI & Guardrails LLM Observability
NICE TO HAVE
Microsoft Copilot Studio Semantic Kernel AutoGen / CrewAI
Deepgram / ElevenLabs LangSmith / Arize / Helicone MLflow / BentoML
Google Gemini / Vertex AI Multimodal AI (Vision + Audio) GraphRAG
EXPERIENCE & QUALIFICATIONS
▸ 5+ years of software engineering experience, with at least 2–3 years focused on AI/ML and GenAI
application development.
▸ Hands-on experience building and deploying LLM-based applications in production — RAG systems,
agents, chatbots, or voicebots.
▸ Strong Python skills; comfortable with async programming, API design, and working across multiple
frameworks simultaneously.
▸ Demonstrable experience with real-time voice AI pipelines or streaming audio applications (LiveKit,
WebRTC, or equivalent).
▸ Experience with at least one major cloud platform (Azure preferred) and containerised deployment.
▸ Prior experience in a services, consulting, or agency environment — managing client relationships and
delivery across multiple projects.
▸ Strong communication skills — able to explain complex AI concepts to non-technical stakeholders clearly
and credibly.
▸ Bachelor's or Master's degree in Computer Science, AI/ML, or related field — or equivalent practical
experience.
▸ Azure AI / OpenAI certifications or equivalent are a plus.
Work Location: In person
