01Overview
Experience: 4.00 yearsSalary: Confidential (based on experience)Expected Notice Period: 7 DaysShift: (GMT05:30) Asia/Kolkata (IST)Opportunity Type: RemotePlacement Type: Full Time Contract for 6 Months(40 hrs a week/160 hrs a month)(*Note: This is a requirement for one of Uplers client - LL)What do you need for this opportunityMust have skills required:Anthropic, Open AI, token budgeting, AI, LLM, MLOps, Vertex, GCP, Machine Learning, PythonLL is Looking for:OverviewWe are supporting an innovative early-stage SaaS company building a first-of-its-kind AI insights platform for commercial teams. The platform analyses customer conversations alongside sales and marketing data to generate actionable insightsautomating strategy workflows that are traditionally manual. With the MVP built and entering its first customer trials, the team is now looking for an experienced Machine Learning Engineer to optimise and production LLM-driven workflows. This role offers the opportunity to shape how AI operates within the productfrom prompt design and output safety to scalable, reliable inference in real-world environments.About The ProjectThis role focuses on delivering practical, high-impact LLM integrations that power the platforms core insight features. Responsibilities include designing robust prompts, deploying inference workflows, and ensuring safe, scalable model behaviour in production.You will work closely with Product and Backend Engineering to embed AI logic into real user flowsenabling contextual, traceable insights with minimal friction. The current stack includes GCP, Vertex AI, Python-based scripting, and a pragmatic, delivery-focused approach.This position is ideal for someone who thrives at the intersection of prompt engineering, MLOps, and production deployment, and who is comfortable shaping early-stage infrastructure while maintaining quality, performance, and safety.Current Phase: Post-MVP Growth & ScalingWith the MVP complete, the focus has shifted from simply getting it to work to:Improving accuracyReducing hallucination riskOptimising cost and performanceThe goal is to evolve early prompt experimentation into a commercially robust, scalable AI engine.The RoleYou will own the AI/ML capability of the platform, ensuring insight generation is:Clear and consistently structuredCost-efficient and low-latencyProduction-grade and measurableYou will help transition the product from experimental prompts into a reliable, scalable system that supports long-term growth.Must-Have Experience & SkillsTechnical / Product23 years of prompt engineering or applied LLM integration experienceStrong understanding of OpenAI, Anthropic, or Vertex AI APIsExperience deploying LLM inference pipelines in productionProficiency in Python and cloud-based backend functionsKnowledge of token budgeting, latency constraints, and output controlExperience with prompt testing, risk mitigation, and hallucination reductionHands-on exposure to vector databases and RAG architectures (required)Exposure to embedding-based tagging (bonus)Understanding of safe, cost-efficient LLM design in early-stage productsBusiness & DeliveryAbility to translate business language and taxonomies into model promptsExperience collaborating with Product Managers and domain expertsStrong judgement around end-user expectations, tone, and insight utilityFamiliarity with privacy, governance, and enterprise data practices (preferred)Soft SkillsStrong collaboration skills across Product, Backend, and Leadership teamsHigh autonomy with a bias for iteration and experimentationClear written and verbal communicationCurious, organised, and highly user-focusedKey ResponsibilitiesPrompt & Model Optimisation: Improve prompt quality, error handling, and structured outputsPerformance Engineering: Optimise token usage, latency, grounding strategies, and hallucination safeguardsEvaluation & Metrics: Define and implement metrics to assess insight quality and reliabilityArchitecture: Contribute to future architecture decisions for content generation and RAG workflowsProduction Lifecycle: Partner with engineering on scalable deployment and model lifecycle managementSuccess CriteriaLLM outputs are relevant, structured, and aligned with business toneInference pipelines are performant, stable, and scalablePrompts support core insight categories (e.g., sentiment, trends, themes)Strong collaboration across product and engineering teamsAI infrastructure enables rapid iteration beyond MVPAdditional InformationEquipment: BYODOnboarding: Intro sessions with engineering, product, and delivery leadsEligibility: Candidates must not be based in regions subject to UK financial sanctionsHow to apply for this opportunityStep 1: Click On Apply! And Register or Login on our portal.Step 2: Complete the Screening Form & Upload updated ResumeStep 3: Increase your chances to get shortlisted & meet the client for the Interview!About Uplers:Our goal is to make hiring reliable, simple, and fast. Our role will .
