Senior Backend Engineer, LLM
Blink Ops
CloudDistributed SystemsDockerGoKubernetesMicroservicesPython
Job Level
Senior
Tech Stack
CloudKotlinKubernetesPython
About the role
- The Senior AI Engineer will be a founding member of our AI capability within the Growth Squad, responsible for applying advanced large language models (LLMs) to solve complex customer and operational challenges. This role will create significant value for Allica by building agentic AI systems that either eliminate manual effort or transform the customer experience — through intelligent automation, smarter interfaces, and proactive service.
- Working closely with growth, data, product, and operations teams, this role will scope, design, and deploy real-world AI use cases across marketing, onboarding, and customer lifecycle journeys (including initiatives in advertising platforms and our CRM, HubSpot). You will bring deep expertise in LLMs, prompt engineering, agent frameworks, and systems thinking to build scalable, explainable, and impactful solutions.
- Own the end-to-end delivery of AI solutions — from idea to production deployment and monitoring — and play a pivotal role in shaping how we scale Allica using AI. You will continuously fine-tune and optimize models for performance, manage their versioning, and establish robust evaluation and monitoring processes to ensure each solution remains reliable, efficient, and safe in production.
- Design and build agentic LLM systems that automate manual processes or transform customer interactions across key stages of the growth funnel.
- Lead the end-to-end development of AI tools and agents using frameworks like LangChain or Semantic Kernel, ensuring scalable and maintainable deployment, including fine-tuning models and optimizing performance to meet latency and cost constraints
- Ensure robust deployment of AI models to production, including proper versioning and continuous monitoring, leveraging tools like MLflow, FastAPI, and Kubernetes (or other cloud-native services) to maintain high reliability and performance
- Identify high-impact use cases with operations, product, and lifecycle teams, creating AI-driven solutions that improve efficiency or elevate customer experience.
- Rapidly prototype AI applications, run experiments to test impact, and iterate based on usage data and feedback.
- Partner with growth, marketing, engineering, and data teams to prioritize AI initiatives, align on business goals, and integrate solutions into operational systems.
- Apply best practices in responsible AI deployment, ensuring explainability, compliance, and ethical use of LLMs in production environments.
- Design and implement rigorous evaluation frameworks (including custom pipelines) to test model performance, quality, and safety. Compare vendor-provided models vs. open-source alternatives for overall quality, bias, and compliance, ensuring we deploy the optimal solutions
- Drive innovation through continuous learning and experimentation, ensuring AI solutions align with Allica’s long-term growth strategy and customer-centric values.
Requirements
- 3+ years’ professional software engineering experience in one or more programming languages (preferably Python and Kotlin)
- Proven experience building and deploying LLM-powered tools or agents (e.g., using OpenAI, Claude, or open-source models)
- Hands-on expertise in Python, LLM frameworks (LangChain, Semantic Kernel, etc.), prompt engineering, and orchestration
- Knowledge of model deployment, versioning, and monitoring in production (e.g., using MLflow, FastAPI, Kubernetes, or similar cloud-native tools)
- Experience integrating AI solutions into real-world systems (e.g., CRM platforms like HubSpot, advertising platforms, ticketing systems, or internal tools)
- Experience fine-tuning and optimizing LLMs, including building efficient embeddings or vector memory stores, while managing latency and cost constraints
- Understanding of privacy, bias, and safety considerations when applying LLMs in production
- Strong understanding of vector databases, RAG (retrieval augmented generation), and agent workflows
- Experience evaluating AI models for quality and fairness, including comparing vendor models vs. open-source alternatives and building custom evaluation pipelines to validate model performance
- Comfortable with full-stack development (e.g., building web interfaces or APIs) to integrate AI solutions end-to-end
- Exposure to business domains like growth, marketing automation, or customer service is a plus
Similar jobs on JobTailor
Staff Software Engineer, Machine Learning
SuperDial
AWSAzureCloudDistributed SystemsDockerGoGoogle Cloud PlatformJavaKubernetesPythonTerraformTypeScript
AI Engineer
Kandji
AirflowAWSCloudDistributed SystemsDockerGoGoogle Cloud PlatformKubernetesMicroservicesPythonPyTorchRay+4 more
Senior Product Manager
Zeta Global
Cloud
AI/ML Architect
3Pillar Global
AWSAzureCloudDockerGoogle Cloud PlatformKubernetesMicroservicesOpen SourcePythonPyTorchScikit-LearnTensorflow