AI Engineer

AJENTIK AI PTE. LTD.; Singapore; On-site; SGD 60,000 - 110,000; Full time

Benefits offered by this job

Health benefits

Flexible work arrangements

Job summary

Ajentik AI Pte. Ltd. in Singapore is hiring an AI Engineer to build end-to-end LLM pipelines for caregiver conversations, extracting structured clinical fields and producing clinician-ready summaries.

You will work directly with the founders and Clinical Lead, delivering production-ready features with privacy and accuracy at the core. The role emphasizes production-grade engineering, testing, and collaboration with a small team to ship to real users, with opportunities to explore advanced

Qualifications

• 1–4 years of professional software engineering experience.
• At least one LLM-powered feature or product built for real users.
• Knowledge of structured outputs, prompt design and LLM failure modes.
• Habit of writing tests and evaluations, not only prompts.
• Solid fundamentals in APIs, SQL, Git, automated testing and CI.
• Clear written English; strong privacy and safety considerations.

Responsibilities

• Build and improve LLM pipelines end to end: conversation design and prompts.
• Turn caregiver conversations into validated clinical fields with traceability.
• Integrate speech-to-text and text-to-speech into low-latency voice conversations.
• Grow evaluation suite with golden sets, synthetic personas and CI tests.
• Monitor quality, cost, and latency; adjust models and prompts accordingly.
• Develop interoperable outputs (JSON, PDF, HL7 FHIR) for hospitals.

Skills

Python

LLM integration

Testing & CI

APIs

SQL

English communication

Privacy awareness

Education

Degree in computer science or related field

Tools

FastAPI

Pydantic

PostgreSQL

pgvector

Docker

Kubernetes

Supabase

vLLM

Model Context Protocol (MCP)

Job description

About Ajentik

Ajentik AI Pte. Ltd. is a Singapore healthtech company incubated at NUSX (formerly NUS Enterprise). We build Elderwise, an AI-powered Comprehensive Geriatric Assessment (CGA) platform that turns caregiver observations into structured, EMR-ready clinical summaries. Caregivers speak with our voice assistant in the browser, with no app to install. Clinicians receive a structured summary to review and file, and families receive a plain-language report. We are in pilot discussions with geriatric teams across Singapore's public healthcare clusters and the community care sector.

About the Role

As an AI Engineer, you will build the conversational and extraction pipelines at the heart of Elderwise: the voice conversation with a caregiver, the structured clinical fields it produces, and the summary a clinician reviews and signs. You will ship to real users in a setting where accuracy, privacy and clinician trust matter more than demo polish.

The role suits an engineer with one to four years of experience who has shipped software to production and wants to go deep on applied LLM engineering. You will work directly with the founders, our engineers and our Clinical Lead, with experienced engineers reviewing your designs and code. Your scope will grow as you show you can own it.

Key Responsibilities

• Build and improve LLM pipelines end to end: conversation design, prompting, structured outputs, schema validation, retries, logging and storage
• Turn caregiver conversations into validated clinical fields, each traceable to what was said and marked as stated, inferred or not asked
• Integrate speech-to-text and text-to-speech into low-latency voice conversations, and catch transcription errors before they reach a clinical document
• Grow our evaluation suite: golden sets, synthetic caregiver personas, adversarial cases and regression checks that run in CI on every prompt or model change
• Track quality, cost and latency per release, and make model and prompt changes on evidence rather than intuition
• Push the boundaries of what our AI can do: prototype next-level capabilities such as emotion and stress detection from voice and conversation, measure them rigorously with our Clinical Lead, and take what works from experiment into the product
• Build guardrails that hold every time: no diagnosis or medical advice, safe escalation paths and defences against prompt injection
• Produce interoperable outputs (structured JSON, PDF reports and HL7 FHIR R4 resources) that fit how hospitals file records
• Handle personal and health data responsibly under PDPA and our ISO 27001 and ISO 42001 programmes, from data minimisation to redacted logs
• Work spec-first with AI coding agents: write the spec and tests, let the agent implement, and own the result
• Join clinician and caregiver sessions to see how the product is used, and turn what you learn into engineering work

Requirements

• 1 to 4 years of professional software engineering experience, with strong Python
• At least one LLM-powered feature or product you built that real users relied on, not only a demo, and the ability to explain what broke and how you fixed it
• Working knowledge of structured outputs, prompt design and the ways LLMs fail, including hallucination, non-determinism and behaviour changes between model versions
• A habit of measuring: you write tests and evaluations, not only prompts
• Solid fundamentals in APIs, SQL, Git, automated testing and CI
• Clear written communication in English, and honesty about what you know and what you don't
• Care for privacy and safety when working with sensitive personal data

Nice to Have

• Experience with voice or speech systems: streaming STT and TTS, turn-taking and realtime audio
• FastAPI and Pydantic, PostgreSQL with pgvector, Supabase, Docker and Kubernetes
• Retrieval (hybrid search, reranking) and agent tool use, including the Model Context Protocol (MCP)
• Serving open-weight models (for example with vLLM) or running small models on device
• Research or prototyping in affective computing, speech emotion recognition or multimodal models
• Healthcare data standards such as HL7 FHIR, or experience in healthtech or another regulated domain
• Conversational Mandarin, Malay or Tamil, to help evaluate multilingual caregiver conversations
• A degree in computer science, engineering or a related field, or equivalent practical experience

What We Offer

• Competitive salary with equity participation
• Real ownership of production AI systems from your first month
• Room to explore new AI capabilities and take the best ideas into production
• Mentorship from experienced engineers, our Clinical Lead and the founders
• Direct contact with the clinicians and caregivers who use what you build
• Access to frontier and open-weight models and modern AI development tooling
• Health benefits and flexible work arrangements
• Learning budget for courses and conferences
• A clear path toward Senior AI Engineer as the engineering team grows

Your Impact

Every